🚀 Flux-Midjourney-Painterly-LoRA
Flux-Midjourney-Painterly-LoRA 是一个文本到图像的模型,基于 LoRA 和 Diffusers 技术,能够根据特定提示生成具有绘画风格的图像,为图像创作带来新的可能。
🚀 快速开始
环境设置
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-Midjourney-Painterly-LoRA"
trigger_word = "mj painterly"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
触发词使用
你应该使用 mj painterly
来触发图像生成。
模型下载
此模型的权重以 Safetensors 格式提供。
点击下载,可在 Files & versions 标签中获取。
✨ 主要特性
- 支持文本到图像的转换,能够根据不同的文本提示生成多样化的图像。
- 采用 LoRA 技术,可高效微调模型。
- 提供多个示例,展示了不同风格和主题的图像生成效果。
📚 详细文档
模型描述

图像处理参数
参数 |
值 |
参数 |
值 |
LR Scheduler |
constant |
Noise Offset |
0.03 |
Optimizer |
AdamW |
Multires Noise Discount |
0.1 |
Network Dim |
64 |
Multires Noise Iterations |
10 |
Network Alpha |
32 |
Repeat & Steps |
25 & 3400 |
Epoch |
20 |
Save Every N Epochs |
1 [40] |
标注信息
标注采用 florence2 - en(自然语言 & 英语)。
训练数据
总共使用 26 张 [Midjourney 生成的合成图像] 进行训练。
最佳尺寸与推理
尺寸 |
宽高比 |
推荐情况 |
1280 x 832 |
3:2 |
最佳 |
1024 x 1024 |
1:1 |
默认 |
推理范围
📄 许可证
本模型使用的许可证为 flux - 1 - dev - non - commercial - license,详细信息请查看 许可证链接。
🔍 示例展示
以下是一些输入文本及对应的输出图像示例:
- **输入文本**:'mj painterly, a monochromatic drawing of a womans face is displayed against a dark blue backdrop. The womans head is angled towards the left side of the frame, her hair cascading over her shoulders. Her eyes are closed, her lips are pursed, and her nose is adorned with a nose ring. Her hair is cut in a bob, adding a touch of depth to the composition.'
**输出图像**:[点击查看](images/111.png)
- **输入文本**:'mj painterly, An animated portrait of a woman with a white t - shirt on a light pink background. The womans head is facing the left side of the frame, her hair is a vibrant shade of blue, with a few wispy bangs on the right side of her head. Her eyebrows are a darker shade of brown, and her lips are a lighter shade of pink. Her eyes are a piercing blue, and she has a slight smile on her face. Her hair is pulled back, framing her face, adding a pop of color to the scene. The background is a pale pink, creating a stark contrast to the womans face.'
**输出图像**:[点击查看](images/222.png)
- **输入文本**:'mj painterly, An animated image of a woman with short green hair. The womans hair is a vibrant shade of green, while her lips are a lighter shade of pink. Her eyes are a darker shade of brown. Her eyebrows are a light shade of red. She is wearing a short sleeve green t - shirt. The background is a light green, and there is a shadow of her head on the right side of the image.'
**输出图像**:[点击查看](images/333.png)
- **输入文本**:'mj painterly, An animated portrait of a woman with long white hair. The woman is wearing a blue dress with a white collar. The background is a light blue color.'
**输出图像**:[点击查看](images/444.png)
- **输入文本**:'mj painterly, A monochromatic drawing of a cat curled up in a sleeping position on a dark teal background. The cats fur is a gradient of greys, and its ears are perked slightly as if listening in sleep. A long tail loops around its body, and the texture of the fur is rendered in delicate strokes, adding depth and softness to the composition.'
**输出图像**:[点击查看](images/555.png)
- **输入文本**:'mj painterly, An animated portrait of a woman with curly orange hair styled in a messy bun. She is wearing a mustard yellow turtleneck sweater. Her freckles are prominent, and her eyes are green and wide. The background is a soft beige with light sketchy shading around her form.'
**输出图像**:[点击查看](images/666.png)